Papers with Code 아카이브
Optical Flow Estimation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 10
- 보존된 평가 기록
- 133
Optical Flow Estimation is a computer vision task that involves computing the motion of objects in an image or a video sequence. The goal of optical flow estimation is to determine the movement of pixels or features in the image, which can be used for various applications such as object tracking, motion analysis, and video compression.
Approaches for optical flow estimation include correlation-based, block-matching, feature tracking, energy-based, and more recently gradient-based.
Further readings:
Definition source: Devon: Deformable Volume Network for Learning Optical Flow
Image credit: Optical Flow Estimation
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Channel-wise Motion Features for Efficient Motion Segmentation
An Efficient Approach for Muscle Segmentation and 3D Reconstruction Using Keypoint Tracking in MRI Scan
Learning to Track Any Points from Human Motion
TLB-VFI: Temporal-Aware Latent Brownian Bridge Diffusion for Video Frame Interpolation
MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation
EndoFlow-SLAM: Real-Time Endoscopic SLAM with Flow-Constrained Gaussian Splatting
WAFT: Warping-Alone Field Transforms for Optical Flow
Feature Hallucination for Self-supervised Action Recognition
Multimodal Fusion SLAM with Fourier Attention
EndoMUST: Monocular Depth Estimation for Robotic Endoscopy via End-to-end Multi-step Self-supervised Training
MOL: Joint Estimation of Micro-Expression, Optical Flow, and Landmark via Transformer-Graph-Style Convolution
Inference-Time Gaze Refinement for Micro-Expression Recognition: Enhancing Event-Based Eye Tracking with Motion-Aware Post-Processing
Post-Training Quantization for Video Matting
Princeton365: A Diverse Dataset with Accurate Camera Pose
UFM: A Simple Path towards Unified Dense Correspondence with Flow
Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images
Spatio-Temporal State Space Model For Efficient Event-Based Optical Flow
EV-LayerSegNet: Self-supervised Motion Segmentation using Event Cameras
Dy3DGS-SLAM: Monocular 3D Gaussian Splatting SLAM for Dynamic Environments
3DFlowAction: Learning Cross-Embodiment Manipulation from 3D Flow World Model
DualX-VSR: Dual Axial Spatial$\times$Temporal Transformer for Real-World Video Super-Resolution without Motion Compensation
Towards a Generalizable Bimanual Foundation Policy via Flow-based Video Prediction
Zero-to-Hero: Zero-Shot Initialization Empowering Reference-Based Video Appearance Editing
A Unified Solution to Video Fusion: From Multi-Frame Learning to Benchmarking
CTRL-GS: Cascaded Temporal Residue Learning for 4D Gaussian Splatting
Brightness-Invariant Tracking Estimation in Tagged MRI
V2V: Scaling Event-Based Vision through Efficient Video-to-Voxel Simulation
Efficient Correlation Volume Sampling for Ultra-High-Resolution Optical Flow Estimation
Just Dance with $π$! A Poly-modal Inductor for Weakly-supervised Video Anomaly Detection
eStonefish-scenes: A synthetically generated dataset for underwater event-based optical flow prediction tasks
RoPECraft: Training-Free Motion Transfer with Trajectory-Guided RoPE Optimization on Diffusion Transformers
MonoMobility: Zero-Shot 3D Mobility Analysis from Monocular Videos
Planar Velocity Estimation for Fast-Moving Mobile Robots Using Event-Based Optical Flow
TartanGround: A Large-Scale Dataset for Ground Robot Perception and Navigation
RobustSpring: Benchmarking Robustness to Image Corruptions for Optical Flow, Scene Flow and Stereo
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.